注释
代码注释与标注
sql-optimizer
xmx0632
分析 MyBatis SQL 并提供优化建议。优化数据库查询时使用。
legacy-support-adjudication
pratyush1712
Use during code review when a change touches backward-compatibility logic, migration shims, deprecated API/version bridges, old schema or payload handling, feature-flag fallbacks, transitional formats, old client support, historical data readers, or retired runtime/build support. Produces an evidence-based verdict: retain, instrument, deprecate, quarantine, or remove.
improving-prompts
cachemoney
Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files for Claude 4.5 models - applies documented Anthropic best practices systematically instead of inventing improvements
just-init
fredericosantos
Navigate Python codebases by reading init.py files before opening other files in a package. Maintain every init.py as living documentation: a top-level docstring containing a one-line package description, a file tree of .py files and subdirectories, and a brief purpose for each entry. Use when: (1) exploring or navigating a Python codebase, (2) creating new Python packages or modules, (3) adding, removing, or renaming files within a Python package, (4) onboarding to an unfamiliar Python project.
research-writing
Nonsteroidevangel872
科研论文写作助手，提供 30 个 Prompt 模板覆盖论文写作全流程。 当用户提到：论文写作、润色、翻译、文献综述、摘要、引言、方法章节、回复审稿人、基金申请、研究计划、学术演讲 PPT、LaTeX 编辑、学术图表、实验结果分析、模拟审稿、去 AI 味、文献对比、找研究空白、论文大纲时使用。
impeccable-onboard
SebastiaanWouters
"Skills-only equivalent of impeccable.style /onboard. Design or improve onboarding flows, empty states, and first-time user experiences. Helps users get started successfully and understand value quickly. Use for frontend and UI design tasks."
abstract-annotation
LHX200013
Extract exact relevant mentions from academic abstracts, group them into dimensions and subdimensions, and generate review-ready article and dimension outputs.
vani-forms-inputs
itsjavi
Handle forms and inputs with explicit updates and focus safety
zodipus-custom-schemas
bratsos
Define custom Zod schemas for Prisma JSON fields using @zodSchema annotations. Use when working with typed JSON, metadata fields, settings objects, complex JSON structures in Prisma, or custom-schemas.ts.
concept-dissector-9step
jysd-ai
Deep concept learning and explanation via a strict 9-step "Concept Dissector" workflow (Overview, Definition, Deconstruct, Mechanism, Ecology, Comparison, Practice, Critique, Synthesis). Use when users ask to understand, teach, benchmark, or critically evaluate a concept and need clear boundaries ("what it is NOT"), trade-offs, practical MRE, pitfalls, and intuitive analogy.
mongodb-indexing-optimization
pluginagentmarketplace
Master MongoDB indexing and query optimization. Learn index types, explain plans, performance tuning, and query analysis. Use when optimizing slow queries, analyzing performance, or designing indexes.
documentation
josavicentevw
Generate and maintain high-quality technical documentation including API docs, README files, architecture documentation, user guides, and code comments. Use when creating documentation, writing README files, documenting APIs, or when user mentions documentation, docs, or technical writing.
readme-generator
physics91
WHEN: README generation/update, project documentation, installation/usage/contribution guides WHAT: Project analysis + sectioned README templates + badges + environment variable docs WHEN NOT: API docs → api-documenter, Code comments → api-documenter
minimal-implementation-explainer
sethmblack
Transform complex technical concepts into minimal, working code implementations that build genuine understanding - the Karpathy pedagogical approach.
documentation-writer
jgarrison929
Use when writing API documentation, READMEs, changelogs, architecture decision records (ADRs), migration guides, onboarding guides, troubleshooting docs, code comments, or any technical documentation task.
SKILL.md — OpenClaw Agent Skill
freaxnx01
Pick a repo under ~/projects/repos via fzf and launch Claude Code — with slot tracking, per-slot Telegram pages, and Remote Control integration.
social-content
LeoYeAI
"When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' 'viral content,' 'what should I post,' 'repurpose this content,' 'tweet ideas,' 'LinkedIn carousel,' 'social media strategy,' or 'grow my following.' Use this for any social media content creation, repurposing, or scheduling task. For broader content strategy, see content-strategy."
backend-module-standards
siteboon
Enforce this repository's TypeScript backend module architecture standards. Use whenever creating, modifying, refactoring, or reviewing backend code under server/, including routes, services, modules, repositories, shared backend code, and backend tests. Do not apply these rules to frontend code or non-backend scaffolding.
input-validation
Hack23
Implement comprehensive input validation to prevent XSS, SQL injection, and command injection attacks with sanitization strategies
md-review
oubakiou
Run the standard markdown review loop end-to-end with the mdxg-redline CLI: send a markdown document to a human reviewer, wait (via Bash polling) for the feedback.json they export, then apply their location-aware inline comments back into the markdown and revise it. Always use this skill when the user wants human-in-the-loop review of markdown with structured JSON feedback — e.g. "send this spec out for review", "get a human to review this before we move on", "have someone redline this doc", "leave inline comments on this draft". Even without an explicit file name or tool name, actively consider this skill for any request involving a human review round, human-in-the-loop checking, redlining, or structured reviewer feedback on a document. The same workflow applies when the user launches it as a slash command like /md-review <path>.
vdjdb-harmonize
antigenomics
Harmonize antigen.gene and antigen.species fields in a VDJdb chunk to canonical VDJdb naming. Detects spurious gene/species names, resolves inconsistencies (same epitope → multiple names), and warns about epitopes that are exact substrings of longer epitopes. Invoked standalone or from /proofread when spurious values are detected.
GitLab
imoonkey
```
pdf-anonymize
jamesconsultingllc
True-redacts PII from PDF, Word (.docx), and Excel (.xlsx) documents before sharing. PDFs have glyphs physically removed and replacement text re-laid; DOCX patches run slices to preserve formatting; XLSX replaces cells, comments, headers, defined names, and properties. Handles names, addresses, account numbers, credit scores, and merchants/stores/phones/cities on transaction lines. Works on ASCII PDFs and modern bank statements with CID-encoded subsetted fonts (BoA, Chase). Single file or directory (with --recursive). Output cannot be recovered via Ctrl+F, pdftotext, or another AI. Trigger on "anonymize/redact/sanitize/de-identify this PDF/Word/Excel", "scrub PII", "remove my name/address", "share this safely" — even when the user just attaches a file and asks to strip identifying info. DO NOT USE FOR visual watermarking, legacy .doc/.xls, or .pptx. Do NOT use nano-pdf — it re-renders pages via image AI and corrupts financial text.
humanizer-en
kadirhanpolat
Remove signs of AI-generated writing from English text. A more robust English humanizer built on Wikipedia's "Signs of AI writing" guide and extended with structural, data, quote, conversational, and domain-specific patterns ported from the Turkish insanlastirici project. Detects 85 universal patterns plus 45 domain-specific guides (LinkedIn, academic, news, SEO blog, e-commerce, corporate, medical, tech, marketing, self-help, travel, video script, education, finance, startup, email, code documentation, dialogue/screenwriting, fashion/beauty, real estate, customer support, parenting, legal writing, scientific paper methods/results/discussion, English regional variation, HR/performance reviews/job descriptions, social media, government/public communications, sports/match analysis, food writing/recipes, podcast/long-form audio scripts, mental health/therapy content, obituaries/eulogies, grant writing/nonprofit communications, architecture/interior design writing, personal finance/budgeting content, event planning/wedding content, pet care/veterinary writing, political/opinion writing, automotive/car review writing, fitness/exercise content, gardening/horticulture writing, museum/cultural institution writing, cybersecurity writing). Adds modes (fast/standard/focused), intervention levels (minimum/medium/ maximum), cluster guide, density score, domain-context legitimacy table, register inconsistency detection, claim list mode, change summary mode, comparative analysis mode, and voice profile estimation.